Hari Prasanna Das
 |
Applied Scientist Amazon AWS Generative AI Innovation Center Email: hpdas (at) berkeley.edu Google Scholar |
Brief Biography
I am an Applied Scientist at the AWS Generative AI Innovation Center, where I design Generative AI, LLMs, and Multimodal Learning based solutions for customer use cases.
I completed my Ph.D. in August 2023 from the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley, advised by Prof. Costas J. Spanos. My research interests lie at the intersection of Generative AI, Deep Learning, Computer Vision, Data-Efficient Machine Learning and Smart Buildings. My undergraduate degree was in Electrical Engineering from Indian Institute of Technology (IIT) Kharagpur.
News
August 2023: My Ph.D. dissertation, Data-Centric Machine Learning for Human-Centric Applications, has been published.
April 2023: I was awarded the C.V. & Daulat Ramamoorthy Distinguished Research Award by the Department of Electrical Engineering and Computer Sciences, UC Berkeley. This award is based on outstanding contributions to a new research area in computer science and engineering.
September 2022: Our paper "Improved Dequantization and Normalization Methods for Tabular Data Pre-Processing in Smart Buildings" was accepted at ACM BuildSys 2022 Conference.
May 2022: I was awarded the Lotfi A. Zadeh Prize by the Department of Electrical Engineering and Computer Sciences, UC Berkeley. This award recognizes a graduating PhD student who has made outstanding contributions to soft computing and its applications.
May 2022: Our paper "Time Series-based Deep Learning Model for Personal Thermal Comfort Prediction" has been accepted at AMLIES Workshop, ACM e-Energy Conference 2022.
December 2021: Our paper "Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data" got accepted at AAAI 2022.
November 2021: Won the Best Poster Award for our work "Unsupervised Personal Thermal Comfort Prediction via Adversarial Domain Adaptation" at ACM BuildSys 2021.
November 2021: Excited to share that a new report with detailed policy recommendations for governments on AI and Climate Change that I co-authored for the Global Partnership on AI, is out! Enjoy reading it here.
October 2021: Our paper "Unsupervised Personal Thermal Comfort Prediction via Adversarial Domain Adaptation" has been accepted at ACM BuildSys 2021.
July 2021: Our paper "CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training" has been accepted for a Spotlight Talk at Workshop on Machine Learning for Data: Automated Creation, Privacy, Bias at International Conference on Machine Learning (ICML) 2021.
July 2021: Our paper "CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training" has been accepted for an Oral Presentation at Workshop on Data-Efficient Machine Learning (DeMaL) at KDD 2021.
April 2021: I am co-organizing the "Tackling Climate Change with Machine Learning" workshop at International Conference on Machine Learning (ICML) 2021, a leading conference on ML. Please consider submitting your relevant research works.
April 2021: I moderated a panel discussion on "The Smart Grid: Harnessing the Power of AI" at the AI LA Earth Summit. [Recording here]
April 2021: Our paper "Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data" has been accepted at ICLR 2021 Workshop on Machine Learning for Preventing and Combating Pandemics.
March 2021: We are organizing "3rd International Workshop on Applied Machine Learning for Intelligent Energy Systems (AMLIES)", co-located with ACM e-Energy Conference 2021 (Virtual). Please consider submitting your work. [Call for Papers]
- January 2021: I gave a talk on "Tackling Climate Change with Machine Learning" at the Terra.do climate school. [Recording here]
October 2020: Our paper "Do Occupants in a Building exhibit patterns in Energy Consumption? Analyzing Clusters in Energy Social Games" has been accepted at NeurIPS 2020 Workshop on Tackling Climate Change with Machine Learning.
August 2020: I am serving as the Head Content GSI (Graduate Student Instructor) for the upper division class "EECS 127/227AT: Optimization Models in Engineering" in its Fall 2020 offering with Prof. Venkat Anantharam.
August 2020: I am co-organizing the Doctoral Consortium on Computational Sustainability 2020, to be held virtually from Oct 17-18, 2020. [Apply here by Sept 11th to participate]
May 2020: Our paper on "Understanding Distributions of Environmental Parameters for Thermal Comfort Study in Singapore" has been accepted at AMLIES Workshop, ACM e-Energy Conference 2020.
April 2020: Research happening in our group has been covered by Wired Magazine. Read it here!
February 2020: Our paper "BISCUIT: Building Intelligent System CUstomer Investment Tools" has been accepted at ICLR 2020 Workshop on Tackling Climate Change with Machine Learning.
February 2020: I am co-organizing the Computational Sustainability Open Graduate Seminar (COGS) series for Spring 2020. The seminars will be every alternate Friday 1.30PM-2.30PM Eastern Time, starting 07th Feb 2020. Please join the meeting if you are interested.
January 2020: We are organizing "2nd International Workshop on Applied Machine Learning for Intelligent Energy Systems (AMLIES)", co-located with ACM e-Energy Conference 2020 at Melbourne, Australia. Please consider submitting your work. [Call for Papers]
October 2019: Our paper "Design, Benchmarking and Graphical Lasso based Explainability Analysis of an Energy Game-Theoretic Framework" has been accepted at NeurIPS 2019 Workshop on Tackling Climate Change with Machine Learning.
October 2019: Our paper "A Novel Graphical Lasso based approach towards Segmentation Analysis in Energy Game-Theoretic Frameworks" has been accepted at ICMLA 2019.
September 2019: Selected to attend Doctoral Consortium on Computational Sustainability at CMU, with a travel funding from NSF.
August 2019: I am in the Technical Program Committee (TPC) of NeurIPS 2019 Workshop on Tackling Climate Change with Machine Learning.
August 2019: I am a Graduate Student Instructor (GSI) for the upper division class "EECS 127/227AT: Optimization Models in Engineering" in its Fall 2019 offering with Prof. Alexandre M. Bayen.
July 2019: Our paper "Personal thermal comfort models with wearable sensors" has been accepted for publication in the Building and Environment Journal.
May 2019: Our paper "Machine Learning empowered Occupancy Sensing for Smart Buildings" has been accepted at Climate Change and AI Workshop, International Conference on Machine Learning (ICML) 2019
April 2019: Our paper "WiFi and Vision Multimodal Learning for Accurate and Robust Device-Free Human Activity Recognition" has been accepted at MULA Workshop, Conference on Computer Vision and Pattern Recognition (CVPR) 2019
January 2019: We are organizing "International Workshop on Applied Machine Learning for Intelligent Energy Systems (AMLIES)", co-located with ACM e-Energy Conference 2019 at Phoenix, Arizona, USA. Please consider submitting your work. [Call for Papers]
December 2018: I am invited to attend the Global Young Scientists Summit (GYSS), 2019 to be held at Singapore in January 2019
November 2018: Our paper "Consensus Adversarial Domain Adaptation" has been accepted at AAAI Conference on Artificial Intelligence 2019
June 2018: Our paper "BISCUIT: Building Intelligent System CUstomer Investment Tool" has been accepted at International Conference on Applied Energy 2018
January 2018: Our paper "Personal thermal comfort models based on physiological parameters measured by wearable sensors" has been accepted at Windsor Conference 2018
